Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis
| Date | Stars |
|---|---|
| 2026-07-24 | 842 |
| 2026-07-25 | 842 |
| 2026-07-28 | 846 |
| 2026-07-30 | 846 |
| 2026-08-06 | 846 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h2 align='center'>Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis</h2>
<div align='center'>
<a href=""><strong>Tianqi Li</strong></a>
·
<a href=""><strong>Ruobing Zheng</strong></a><sup>†</sup>
·
<a href=""><strong>Minghui Yang</strong></a>
·
<a href=""><strong>Jingdong Chen</strong></a>
·
<a href=""><strong>Ming Yang</strong></a>
</div>
<div align='center'>
Ant Group
</div>
<br>
<div align='center'>
<a href='https://arxiv.org/abs/2411.19509'><img src='https://img.shields.io/badge/Paper-arXiv-red'></a>
<a href='https://digital-avatar.github.io/ai/Ditto/'><img src='https://img.shields.io/badge/Project-Page-blue'></a>
<a href='https://huggingface.co/digital-avatar/ditto-talkinghead'><img src='https://img.shields.io/badge/Model-HuggingFace-yellow'></a>
<a href='https://github.com/antgroup/ditto-talkinghead'><img src='https://img.shields.io/badge/Code-GitHub-purple'></a>
<!-- <a href='https://github.com/antgroup/ditto-talkinghead'><img src='https://img.shields.io/github/stars/antgroup/ditto-talkinghead?style=social'></a> -->
<a href='https://colab.research.google.com/drive/19SUi1TiO32IS-Crmsu9wrkNspWE8tFbs?usp=sharing'><img src='https://img.shields.io/badge/Demo-Colab-orange'></a>
</div>
<br>
<div align="center">
<video style="width: 95%; object-fit: cover;" controls loop src="https://github.com/user-attachments/assets/ef1a0b08-bff3-4997-a6dd-62a7f51cdb40" muted="false"></video>
<p>
✨ For more results, visit our <a href="https://digital-avatar.github.io/ai/Ditto/"><strong>Project Page</strong></a> ✨
</p>
</div>
## 📌 Updates
* [2025.11.12] 🔥🔥 We noticed the community's enthusiasm for open-source training code. [Training code](https://github.com/antgroup/ditto-talkinghead/tree/train) is now available, since there have been multiple versions and limited time to organize, it may differ slightly from the paper version.
* [2025.07.11] 🔥 The [PyTorch model](#-pytorch-model) is now available.
* [2025.07.07] 🔥 Ditto is accepted by ACM MM 2025.
* [2025.01.21] 🔥 We update the [Colab](https://colab.research.google.com/drive/19SUi1TiO32IS-Crmsu9wrkNspWE8tFbs?usp=sharing) demo, welcome to try it.
* [2025.01.10] 🔥 We release our inference [codes](https://github.com/antgroup/ditto-talkinghead) and [models](https://huggingface.co/digital-avatar/ditto-talkinghead).
* [2024.11.29] 🔥 Our [paper](https://arxiv.org/abs/2411.19509) is in public on arxiv.
## 🔍 Overview
<!-- This is the **train branch**, containing code for **training the model**. For inference code, please switch to the [`main`](https://github.com/antgroup/ditto-talkinghead) branch. -->
This is the **inference branch**. For training code, please switch to the [`train`](https://github.com/antgroup/ditto-talkinghead/tree/train) branch.
## 🛠️ Installation
Tested Environment
- System: Centos 7.2
- GPU: A100
- Python: 3.10
- tensorRT: 8.6.1
Clone the codes from [GitHub](https://github.com/antgroup/ditto-talkinghead):
```bash
git clone https://github.com/antgroup/ditto-talkinghead
cd ditto-talkinghead
```
### Conda
Create `conda` environment:
```bash
conda env create -f environment.yaml
conda activate ditto
```
### Pip
If you have problems creating a conda environment, you can also refer to our [Colab](https://colab.research.google.com/drive/19SUi1TiO32IS-Crmsu9wrkNspWE8tFbs?usp=sharing).
After correctly installing `pytorch`, `cuda` and `cudnn`, you only need to install a few packages using pip:
```bash
pip install \
tensorrt==8.6.1 \
librosa \
tqdm \
filetype \
imageio \
opencv_python_headless \
scikit-image \
cython \
cuda-python \
imageio-ffmpeg \
colored \
polygraphy \
numpy==2.0.1
```
If you don't use `conda`, you may also need to install `ffmpeg` according to the [official website](https://www.ffmpeg.org/download.html).
## 📥 Download Checkpoints
Download checkpoints from [HuggingFace](https://huExcerpt of 8,658 characters
Read on GitHub
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c0c7ff1109540003, topic:video-generation, topic:talking-head, desc:talking head